The Double-Edged Sword of Open-Ended Interaction: How LLM-Driven NPCs Affect Players' Cognitive Load and Gaming Experience

TL;DR

This study investigates how large language model-driven NPCs impact players' cognitive load and gaming experience, revealing increased load and mixed effects on perceived autonomy, with variations across scenarios and individual traits.

Contribution

It provides empirical evidence on the effects of LLM-NPCs on players, highlighting the scenario-sensitive and user-sensitive nature of their impact.

Findings

LLM-NPCs significantly increase cognitive load (p < .001).

No significant improvement in overall gaming experience (p = .195).

Effects vary across different game modules and player traits.

Abstract

This study examines how large language model-driven non-player characters (LLM-NPCs) affect players' cognitive load and gaming experience, with a particular focus on the underlying psychological mechanisms, differences across task scenarios, and the role of individual traits. Conducting a randomized between-subject experiment (N=130) in a self-developed game prototype "Campus Culture Week", we compared player interactions with LLM-NPCs and traditional pre-scripted NPCs across multiple interactive modules. The results showed that LLM-NPCs significantly increased players' cognitive load (p < .001), an effect mediated by factors such as expressive effort and response uncertainty. However, LLM-NPCs did not yield a statistically significant improvement in overall gaming experience (p = .195); while they positively influenced players' perceived autonomy, they exerted a negative influence on system usability and trust. The effects of LLM-NPCs also significantly varied across task scenarios (p < .001), with stronger increases in cognitive load in more open-ended modules such as content creation and relationship building. The influence of individual differences was generally limited, although the personality traits of extraversion (p = .031) and neuroticism (p = .047) demonstrated some predictive power regarding cognitive load. This study provides empirical evidence for understanding the "double-edged sword" effect of LLM-NPCs on player experience, and highlight the importance of scenario-sensitive and user-sensitive design in intelligent NPC systems.